Capitol News

Researchers from Michigan State University and Corewell Health analyzed de-identified electronic health records of over 1.5 million patients to examine the incidence rates and risk factors of mild cognitive impairment (MCI) in rural and urban areas of West Michigan. This study is the first in the state to employ this method.

The results indicated that many MCI cases might be undetected in rural communities. Future research aims to use these findings to develop artificial intelligence tools for earlier identification of the condition.

Published in Alzheimer's & Dementia: Translational Research & Clinical Interventions, the retrospective study utilized 10 years of historical patient data. It represents a large-scale analysis covering most of West Michigan's population, with some unexpected findings.

“While we had our suspicions about what we would find, we did not expect the potential rate of underdiagnosis of MCI in some of the rural areas in West Michigan to be so high,” said Bin Chen, associate professor at MSU College of Human Medicine and co-principal investigator.

Chen noted that individuals typically experience MCI before developing dementia. However, the study found that patients who progressed directly to dementia without an MCI diagnosis were three times more prevalent than those initially identified with MCI.

“This tells us MCI may be going unreported with some patients,” Chen added.

David Chesla, co-principal investigator and senior director of research data management at Corewell Health Research Institute in Grand Rapids, concurred. He stated that underreporting might contribute to lower MCI incidence rates observed in their study compared to national averages.

“Our hypothesis from the beginning was that we would have underreporting of cognitive impairment in communities across West Michigan; we just didn’t know to what extent,” Chesla said. “Our suspicion was initially derived from national data reporting a growing incidence rate of MCI within our aging U.S. population.”

National averages range from 10% to 18%, depending on race, age, and timeframe. The study showed significantly lower incidence rates in West Michigan.

Chesla also mentioned that by examining geographic distribution—urban versus rural locations—they found further evidence supporting potential underreporting. The ratio of "MCI skippers" (patients progressing directly to dementia without an MCI diagnosis) was 4.3 times higher in rural areas compared to 2.8 times in urban areas.

While limited access to care and other factors could drive higher underreporting rates, Chesla acknowledged a limitation: using data from when electronic record systems were less integrated could fragment records contributing to underreporting.

Additional findings revealed similar risk factors for MCI between rural and urban populations; however, urban areas showed a broader array including being African American and having conditions like hearing loss or obstructive sleep apnea among others. Common contributing factors include diabetes, stroke, Parkinson’s disease, and older age.

The researchers aim to leverage AI with this extensive data set for building machine learning models capable of identifying high-risk patients earlier statewide and potentially nationwide. Early diagnosis is crucial for potentially reversing or delaying cognitive impairment progression.

“The goal is to integrate this tool into health care systems everywhere so it can assist physicians in detecting and managing MCI patients more effectively,” Chen said.

Chesla advised individuals experiencing symptoms such as hearing loss or mood swings not hesitate to consult their physician or healthcare provider promptly due to available care plans that can slow or reverse cognitive impairment if caught early.

The study was co-led by Xiaodan Zhang from MSU College of Human Medicine and Martin Witteveen-Lane from Corewell Health, supported by Corewell Health-MSU Alliance and National Institutes of Health.

___